feat(cli): add tools fine_tunes.prepare_data

Author: stainless-bot

src/openai/cli/_cli.py

@@ -90,7 +90,8 @@ def help() -> None:
 
     register_commands(sub_api)
 
-    _tools.register_commands(subparsers)
+    sub_tools = subparsers.add_parser("tools", help="Client side tools for convenience")
+    _tools.register_commands(sub_tools, subparsers)
 
     return parser
 

src/openai/cli/_tools/_main.py

@@ -3,11 +3,15 @@
 from typing import TYPE_CHECKING
 from argparse import ArgumentParser
 
-from . import migrate
+from . import migrate, fine_tunes
 
 if TYPE_CHECKING:
     from argparse import _SubParsersAction
 
 
-def register_commands(subparser: _SubParsersAction[ArgumentParser]) -> None:
+def register_commands(parser: ArgumentParser, subparser: _SubParsersAction[ArgumentParser]) -> None:
     migrate.register(subparser)
+
+    namespaced = parser.add_subparsers(title="Tools", help="Convenience client side tools")
+
+    fine_tunes.register(namespaced)

src/openai/cli/_tools/fine_tunes.py

@@ -0,0 +1,63 @@
+from __future__ import annotations
+
+import sys
+from typing import TYPE_CHECKING
+from argparse import ArgumentParser
+
+from .._models import BaseModel
+from ...lib._validators import (
+    get_validators,
+    write_out_file,
+    read_any_format,
+    apply_validators,
+    apply_necessary_remediation,
+)
+
+if TYPE_CHECKING:
+    from argparse import _SubParsersAction
+
+
+def register(subparser: _SubParsersAction[ArgumentParser]) -> None:
+    sub = subparser.add_parser("fine_tunes.prepare_data")
+    sub.add_argument(
+        "-f",
+        "--file",
+        required=True,
+        help="JSONL, JSON, CSV, TSV, TXT or XLSX file containing prompt-completion examples to be analyzed."
+        "This should be the local file path.",
+    )
+    sub.add_argument(
+        "-q",
+        "--quiet",
+        required=False,
+        action="store_true",
+        help="Auto accepts all suggestions, without asking for user input. To be used within scripts.",
+    )
+    sub.set_defaults(func=prepare_data, args_model=PrepareDataArgs)
+
+
+class PrepareDataArgs(BaseModel):
+    file: str
+
+    quiet: bool
+
+
+def prepare_data(args: PrepareDataArgs) -> None:
+    sys.stdout.write("Analyzing...\n")
+    fname = args.file
+    auto_accept = args.quiet
+    df, remediation = read_any_format(fname)
+    apply_necessary_remediation(None, remediation)
+
+    validators = get_validators()
+
+    assert df is not None
+
+    apply_validators(
+        df,
+        fname,
+        remediation,
+        validators,
+        auto_accept,
+        write_out_file_func=write_out_file,
+    )